ICML 2024 Papers

When selecting data for training large-scale models, standard practice is to filter for examples that match human notions of data quality. Such filtering yields qualitatively clean datapoints that intuitively should improve model behavior. However, in practice the opposite can often happen: we find that selecting according to similarity with "high quality" data sources may not increase (and can even hurt) performance compared to randomly selecting data. To develop better methods for selecting data, we start by framing dataset selection as an optimization problem that we can directly solve for: given target tasks, a learning algorithm, and candidate data, select the subset that maximizes model performance. This framework thus avoids handpicked notions of data quality, and instead models explicitly how the learning process uses train datapoints to predict on the target tasks. Our resulting method greatly improves language model (LM) performance on both pre-specified tasks and previously unseen tasks. Specifically, choosing target tasks representative of standard LM problems and evaluating on diverse held-out benchmarks, our selected datasets provide a 2x compute multiplier over baseline methods.

Fast adapting to unknown peers (partners or opponents) with different strategies is a key challenge in multi-agent games. To do so, it is crucial for the agent to probe and identify the peer’s strategy efficiently, as this is the prerequisite for carrying out the best response in adaptation. However, exploring the strategies of unknown peers is difficult, especially when the games are partially observable and have a long horizon. In this paper, we propose a peer identification reward, which rewards the learning agent based on how well it can identify the behavior pattern of the peer over the historical context, such as the observation over multiple episodes. This reward motivates the agent to learn a context-aware policy for effective exploration and fast adaptation, i.e., to actively seek and collect informative feedback from peers when uncertain about their policies and to exploit the context to perform the best response when confident. We evaluate our method on diverse testbeds that involve competitive (Kuhn Poker), cooperative (PO-Overcooked), or mixed (Predator-Prey-W) games with peer agents. We demonstrate that our method induces more active exploration behavior, achieving faster adaptation and better outcomes than existing methods.

Deep neural networks, including transformers and convolutional neural networks (CNNs), have significantly improved multivariate time series classification (MTSC). However, these methods often rely on supervised learning, which does not fully account for the sparsity and locality of patterns in time series data (e.g., quantification of diseases-related anomalous points in ECG and abnormal detection in signal). To address this challenge, we formally discuss and reformulate MTSC as a weakly supervised problem, introducing a novel multiple-instance learning (MIL) framework for better localization of patterns of interest and modeling time dependencies within time series. Our novel approach, TimeMIL, formulates the temporal correlation and ordering within a time-aware MIL pooling, leveraging a tokenized transformer with a specialized learnable wavelet positional token. The proposed method surpassed 26 recent state-of-the-art MTSC methods, underscoring the effectiveness of the weakly supervised TimeMIL in MTSC. The code is available https://github.com/xiwenc1/TimeMIL.

Recently, there has been a surge in interest in developing optimization algorithms for overparameterized models as achieving generalization is believed to require algorithms with suitable biases. This interest centers on minimizing sharpness of the original loss function; the Sharpness-Aware Minimization (SAM) algorithm has proven effective. However, most literature only considers a few sharpness measures, such as the maximum eigenvalue or trace of the training loss Hessian, which may not yield meaningful insights for non-convex optimization scenarios like neural networks. Additionally, many sharpness measures are sensitive to parameter invariances in neural networks, magnifying significantly under rescaling parameters. Motivated by these challenges, we introduce a new class of sharpness measures in this paper, leading to new sharpness-aware objective functions. We prove that these measures are *universally expressive*, allowing any function of the training loss Hessian matrix to be represented by appropriate hyperparameters. Furthermore, we show that the proposed objective functions explicitly bias towards minimizing their corresponding sharpness measures, and how they allow meaningful applications to models with parameter invariances (such as scale-invariances). Finally, as instances of our proposed general framework, we present *Frob-SAM* and *Det-SAM*, which are specifically designed to minimize the Frobenius norm and the determinant of the Hessian of the training loss, respectively. We also demonstrate the advantages of our general framework through extensive experiments.

Transformer-based architectures achieved breakthrough performance in natural language processing and computer vision, yet they remain inferior to simpler linear baselines in multivariate long-term forecasting. To better understand this phenomenon, we start by studying a toy linear forecasting problem for which we show that transformers are incapable of converging to their true solution despite their high expressive power. We further identify the attention of transformers as being responsible for this low generalization capacity. Building upon this insight, we propose a shallow lightweight transformer model that successfully escapes bad local minima when optimized with sharpness-aware optimization. We empirically demonstrate that this result extends to all commonly used real-world multivariate time series datasets. In particular, SAMformer surpasses current state-of-the-art methods and is on par with the biggest foundation model MOIRAI while having significantly fewer parameters. The code is available at https://github.com/romilbert/samformer.

In federated learning (FL), the multi-step update and data heterogeneity among clients often lead to a loss landscape with sharper minima, degenerating the performance of the resulted global model. Prevalent federated approaches incorporate sharpness-aware minimization (SAM) into local training to mitigate this problem. However, the local loss landscapes may not accurately reflect the flatness of global loss landscape in heterogeneous environments; as a result, minimizing local sharpness and calculating perturbations on client data might not align the efficacy of SAM in FL with centralized training. To overcome this challenge, we propose FedLESAM, a novel algorithm that locally estimates the direction of global perturbation on client side as the difference between global models received in the previous active and current rounds. Besides the improved quality, FedLESAM also speed up federated SAM-based approaches since it only performs once backpropagation in each iteration. Theoretically, we prove a slightly tighter bound than its original FedSAM by ensuring consistent perturbation. Empirically, we conduct comprehensive experiments on four federated benchmark datasets under three partition strategies to demonstrate the superior performance and efficiency of FedLESAM.

Offline data are both valuable and practical resources for teaching robots complex behaviors. Ideally, learning agents should not be constrained by the scarcity of available demonstrations, but rather generalize beyond the training distribution. However, the complexity of real-world scenarios typically requires huge amounts of data to prevent neural network policies from picking up on spurious correlations and learning non-causal relationships. We propose CAIAC, a data augmentation method that can create feasible synthetic transitions from a fixed dataset without having access to online environment interactions. By utilizing principled methods for quantifying causal influence, we are able to perform counterfactual reasoning by swapping $\textit{action}$-unaffected parts of the state-space between independent trajectories in the dataset. We empirically show that this leads to a substantial increase in robustness of offline learning algorithms against distributional shift.

In coming up with solutions to real-world problems, humans implicitly adhere to constraints that are too numerous and complex to be specified completely. However, reinforcement learning (RL) agents need these constraints to learn the correct optimal policy in these settings. The field of Inverse Constraint Reinforcement Learning (ICRL) deals with this problem and provides algorithms that aim to estimate the constraints from expert demonstrations collected offline. Practitioners prefer to know a measure of confidence in the estimated constraints, before deciding to use these constraints, which allows them to only use the constraints that satisfy a desired level of confidence. However, prior works do not allow users to provide the desired level of confidence for the inferred constraints. This work provides a principled ICRL method that can take a confidence level with a set of expert demonstrations and outputs a constraint that is at least as constraining as the true underlying constraint with the desired level of confidence. Further, unlike previous methods, this method allows a user to know if the number of expert trajectories is insufficient to learn a constraint with a desired level of confidence, and therefore collect more expert trajectories as required to simultaneously learn constraints with the desired level of confidence and a policy that achieves the desired level of performance.

Instrumental variable (IV) regression can be approached through its formulation in terms of conditional moment restrictions (CMR). Building on variants of the generalized method of moments, most CMR estimators are implicitly based on approximating the population data distribution via reweightings of the empirical sample. While for large sample sizes, in the independent identically distributed (IID) setting, reweightings can provide sufficient flexibility, they might fail to capture the relevant information in presence of corrupted data or data prone to adversarial attacks. To address these shortcomings, we propose the Sinkhorn Method of Moments, an optimal transport-based IV estimator that takes into account the geometry of the data manifold through data-derivative information. We provide a simple plug-and-play implementation of our method that performs on par with related estimators in standard settings but improves robustness against data corruption and adversarial attacks.

Fairness has become a crucial aspect in the development of trustworthy machine learning algorithms. Current fairness metrics to measure the violation of demographic parity have the following drawbacks: (i) the *average difference* of model predictions on two groups cannot reflect their *distribution disparity*, and (ii) the *overall* calculation along all possible predictions conceals the *extreme local disparity* at or around certain predictions. In this work, we propose a novel fairness metric called **M**aximal **C**umulative ratio **D**isparity along varying **P**redictions' neighborhood (MCDP), for measuring the maximal local disparity of the fairness-aware classifiers. To accurately and efficiently calculate the MCDP, we develop a provably exact and an approximate calculation algorithm that greatly reduces the computational complexity with low estimation error. We further propose a bi-level optimization algorithm using a differentiable approximation of the MCDP for improving the algorithmic fairness. Extensive experiments on both tabular and image datasets validate that our fair training algorithm can achieve superior fairness-accuracy trade-offs.

Federated Learning is widely employed to tackle distributed sensitive data. Existing methods primarily focus on addressing in-federation data heterogeneity. However, we observed that they suffer from significant performance degradation when applied to unseen clients for out-of-federation (OOF) generalization. The recent attempts to address generalization to unseen clients generally struggle to scale up to large-scale distributed settings due to high communication or computation costs. Moreover, methods that scale well often demonstrate poor generalization capability. To achieve OOF-resiliency in a scalable manner, we propose Topology-aware Federated Learning (TFL) that leverages client topology - a graph representing client relationships - to effectively train robust models against OOF data. We formulate a novel optimization problem for TFL, consisting of two key modules: Client Topology Learning, which infers the client relationships in a privacy-preserving manner, and Learning on Client Topology, which leverages the learned topology to identify influential clients and harness this information into the FL optimization process to efficiently build robust models. Empirical evaluation on a variety of real-world datasets verifies TFL's superior OOF robustness and scalability.

The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability approaches either focus solely on node-wise importance or neglect the graph structure when perturbing the input instance. This paper introduces the Myerson-Taylor interaction index that internalizes the graph structure into attributing the node values and the interaction values among nodes. Unlike the Shapley-based methods, the Myerson-Taylor index decomposes coalitions into components satisfying a pre-chosen connectivity criterion. We prove that the Myerson-Taylor index is the unique one that satisfies a system of five natural axioms accounting for graph structure and high-order interaction among nodes. Leveraging these properties, we propose Myerson-Taylor Structure-Aware Graph Explainer (MAGE), a novel explainer that uses the second-order Myerson-Taylor index to identify the most important motifs influencing the model prediction, both positively and negatively. Extensive experiments on various graph datasets and models demonstrate that our method consistently provides superior subgraph explanations compared to state-of-the-art methods.

Adversarial Training (AT), which adversarially perturb the input samples during training, has been acknowledged as one of the most effective defenses against adversarial attacks, yet suffers from inevitably decreased clean accuracy. Instead of perturbing the samples, Sharpness-Aware Minimization (SAM) perturbs the model weights during training to find a more flat loss landscape and improve generalization. However, as SAM is designed for better clean accuracy, its effectiveness in enhancing adversarial robustness remains unexplored. In this work, considering the duality between SAM and AT, we investigate the adversarial robustness derived from SAM. Intriguingly, we find that using SAM alone can improve adversarial robustness. To understand this unexpected property of SAM, we first provide empirical and theoretical insights into how SAM can implicitly learn more robust features, and conduct comprehensive experiments to show that SAM can improve adversarial robustness notably without sacrificing any clean accuracy, shedding light on the potential of SAM to be a substitute for AT when accuracy comes at a higher priority. Code is available at https://github.com/weizeming/SAM_AT.

The varying significance of distinct primitive behaviors during the policy learning process has been overlooked by prior model-free RL algorithms. Leveraging this insight, we explore the causal relationship between different action dimensions and rewards to evaluate the significance of various primitive behaviors during training. We introduce a causality-aware entropy term that effectively identifies and prioritizes actions with high potential impacts for efficient exploration. Furthermore, to prevent excessive focus on specific primitive behaviors, we analyze the gradient dormancy phenomenon and introduce a dormancy-guided reset mechanism to further enhance the efficacy of our method. Our proposed algorithm, **ACE**: Off-policy **A**ctor-critic with **C**ausality-aware **E**ntropy regularization, demonstrates a substantial performance advantage across 29 diverse continuous control tasks spanning 7 domains compared to model-free RL baselines, which underscores the effectiveness, versatility, and efficient sample efficiency of our approach. Benchmark results and videos are available at https://ace-rl.github.io/.